Research Article
Online Traffic Accident Spatial-Temporal Post-Impact Prediction Model on Highways Based on Spiking Neural Networks
Table 8
Prediction performance comparison of queue length.
| Method | 4-lane (19%) | 5-lane (27%) | 6-lane (54%) | Average | MAPE (%) | RMSE | MAPE (%) | RMSE | MAPE (%) | RMSE | MAPE (%) | RMSE |
| Shockwave theory | 30.03 | 0.17 | 28.98 | 0.15 | 36.79 | 0.15 | 33.40 | 0.15 | Nonlinear regression | 22.30 | 0.13 | 21.07 | 0.13 | 27.09 | 0.12 | 24.55 | 0.12 | ANNs | 22.09 | 0.12 | 23.50 | 0.10 | 26.85 | 0.08 | 25.04 | 0.09 | CNNs (ours) | 16.81 | 0.07 | 15.06 | 0.06 | 20.77 | 0.05 | 18.48 | 0.06 |
|
|